Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Light Acquisition

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Explainable detection of goldenhar syndrome using an OD-Mamba backbone for rare craniofacial disorder diagnosis.

Scientific reports·2026

Same author

Computational discovery of emodin-based anthraquinones as PARP-1 inhibitors with relevance to ovarian and prostate cancer.

Scientific reports·2026

Same author

Domain-robust vision transformer with hierarchical swin encoding for explainable low-latency driver drowsiness detection.

Scientific reports·2026

Same author

Tramadol-Induced Persistent Singultus: A Case Report on Diagnosis, Mechanism, and Management.

Clinical case reports·2026

Same author

Immunotoxic Impact of Bisphenol A (BPA) on Aquatic and Human Immune System.

Journal of applied toxicology : JAT·2026

Same author

CDK7 as a Potential Exploratory Biomarker for Distinguishing Acute Myocardial Infarction Subtypes via DDR Pathways: Evidence From a Bangladeshi Cohort.

Clinical cardiology·2026

Search research articles

相关实验视频

Updated: Mar 23, 2026

Remote Sensing Evaluation of Two-spotted Spider Mite Damage on Greenhouse Cotton

Remote Sensing Evaluation of Two-spotted Spider Mite Damage on Greenhouse Cotton

Published on: April 28, 2017

可解释的变压器框架用于快速的棉花叶诊断和织物缺陷检测.

S M Masfequier Rahman Swapno¹, Anamul Sakib², Al Shahriar Uddin Khondakar Pranta³

¹Department Of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka 1216, Bangladesh.

|February 20, 2026

概括

一个新的混合深度学习模型使用可解释AI (XAI) 准确地分类棉花叶病和织物缺陷. 这种高效的框架为农业和织品质量评估提供了高性能.

关键词:

农业植物产品农业植物产品植物与生物体的相互作用.植物生物信息学植物生物信息学植物生物技术植物生物技术

更多相关视频

A Simple and Scalable Fabrication Method for Organic Electronic Devices on Textiles

A Simple and Scalable Fabrication Method for Organic Electronic Devices on Textiles

Published on: March 13, 2017

Fabricating Cotton Analytical Devices

Fabricating Cotton Analytical Devices

Published on: August 30, 2016

相关实验视频

Last Updated: Mar 23, 2026

Remote Sensing Evaluation of Two-spotted Spider Mite Damage on Greenhouse Cotton

Remote Sensing Evaluation of Two-spotted Spider Mite Damage on Greenhouse Cotton

Published on: April 28, 2017

A Simple and Scalable Fabrication Method for Organic Electronic Devices on Textiles

A Simple and Scalable Fabrication Method for Organic Electronic Devices on Textiles

Published on: March 13, 2017

Fabricating Cotton Analytical Devices

Fabricating Cotton Analytical Devices

Published on: August 30, 2016

科学领域:

人工智能的人工智能
计算机视觉计算机视觉
机器学习机器学习

背景情况:

准确识别棉花叶病和织物缺陷对于农业产量和织品质量至关重要.
现有的AI模型往往缺乏可解释性或计算效率.

研究的目的:

开发一种混合深度学习模型,将CNN和视觉转换器结合起来,用于分类棉花叶病和织物缺陷.
使用可解释AI (XAI) 技术增强模型的解释性.
在人工智能驱动的质量评估中实现高精度和计算效率.

主要方法:

一个混合深度学习模型,集成基于CNN的层次特征提取和视觉转换器自我注意 (XCottL-FebViT).
可解释AI (XAI) 的应用,以提高模型的可解释性.
对计算效率进行超参数优化.
在四个基准数据集上进行评估:CottonLeafNet,SAR-CLD,CottonFabricImageBD和FabricSpotDefect.

主要成果:

与现有的基于变压器的模型相比,XCottL-FebViT表现出更高的性能.
取得了很高的培训和验证准确度 (例如,CottonLeafNet的培训率为99.97%和验证率为99.93%).
在数据集中的准确性,MCC和F1分数的持续改进.

结论:

拟议的XCottL-FebViT模型为检测棉花叶病和织物缺陷提供了一个高度准确,可解释和计算高效的解决方案.
集成XAI为领域专家更好地理解和信任人工智能决策.
一个实用的基于网络的应用程序可以实现远程部署,用于在农业和织品中进行现实世界的质量评估.